Productivity & Workflow Agent Skills for Claude Code

Audits a prompt against the actual codebase, docs, and strategy files — separates fact from invention, finds what's already built…

Transform weak prompts into high-performance prompts for OpenAI and Codex workflows by asking targeted clarifying questions, preserving…

WHEN refining or structuring prompts; NOT executing tasks; outputs XML-tagged instructions with roles, tasks, constraints, and examples.

Analyze a draft prompt, critique it, match it to ECC ecosystem components, and output a complete optimized prompt the user can paste and…

Orchestrates parallel prompt validation for Finesse planning sessions

Use when Codex should work as a coding-agent-native proof planning and review workflow: transform a candidate theorem, proof sketch…

Refactor a completed, research-loop-validated proof closure into a compact, locally checkable proof, minimal derived proof DAG, and…

Use when pitching a survey to the Journal of Economic Literature (JEL) editor before writing it — the ~10-page proposal route, the…

Generate PandaDoc proposals from client information or sales call transcripts.

Stress-tests product proposals, architecture designs, and technical plans through structured adversarial questioning and failure mode…

Develop, compare, and recommend among multiple plausible fixes for a problem.

PROPOSE-ONLY — mine this host's recent Claude Code transcripts for work that keeps recurring and keeps returning bulk into context, rank…

Prototype mode — the reduced gate set for a throwaway repo that answers one question and then gets deleted, plus the expiry and graduation…

Convert an already substantially defined product prototype into an engineering-ready PRD by identifying specification gaps, applying only…

Guides validation of ideas before full development using pretotyping (fake doors, concierge MVPs, Wizard of Oz) and prototyping at…

Retrieve and maintain a small provenance-aware project memory when an earlier fact, correction, decision, or unresolved item affects…

Guides safe, read-only system investigations, repository exploration, and query execution without triggering unintended permissions or…

Use as the entry point for any Psychological Bulletin manuscript.

Use when deciding which psychrev-* sub-skill to invoke next, or when sequencing a theory or formal-model manuscript from problem framing…

Unified task management and scheduling for AI agents.

Reads PRDs, architectural invariants, and cross-repo contracts from documentation hubs to align technical requirements before…